Ensemble learning-based classification models for slope stability analysis

Abstract

In this study, ensemble learning was applied to develop a classification model capable of accurately estimating slope stability. Two prominent ensemble techniques-parallel learning and sequential learning-were applied to implement the ensemble classifiers. Additionally, for comparison, eight versatile machine learning algorithms were utilized to formulate the single-learning classification models. These classification models were trained and evaluated on the well-established global database of slope documented from 1930 to 2005. The performance of these classification models was measured by considering the F-1 score, accuracy, receiver operating characteristic (ROC) curve and area under the ROC curve (AUC). Furthermore, K-fold cross-validation was employed to fairly assess the generalization capacity of these models. The obtained results demonstrated the advantage of ensemble classifiers over single-learning classification models. When ensemble learning was used instead of the single learning, the average F-1 score, accuracy, and AUC of the models increased by 2.17%, 1.66%, and 6.27%, respectively. In particular, the ensemble classifiers with sequential learning exhibited better performance than those with parallel learning. The ensemble classifiers on the extreme gradient boosting (XGB-CM) framework clearly provided the best performance on the test set, with the highest F-1 score, accuracy, and AUC of 0.914, 0.903, and 0.95, respectively. The excellent performance on the spatially well-distributed database along with its capacity to distribute computing indicates the significant potential applicability of the presented ensemble classifiers, particularly the XGB-CM, for landslide risk assessment and management on a global scale.